© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210407
    Prev
    Next
    INDEX
    Explanations

    goal for me, tax rate, bidding, useful metric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subspaces
    0.18
    ίου
    0.18
    Morgan
    0.18
     ಕಾಲ
    0.18
    Ely
    0.18
    ᅬ
    0.17
    𒄿
    0.17
     chargés
    0.17
    ４
    0.17
    ിയുടെ
    0.17
    POSITIVE LOGITS
    led
    0.19
    lier
    0.17
    impul
    0.16
    able
    0.16
     betray
    0.16
    programme
    0.15
     aggressive
    0.15
     kann
    0.15
     aggression
    0.15
    än
    0.15
    Activations Density 0.000%

    No Known Activations